Analysing the RLHF pipeline
Russel
rshwndsz
·
AI & ML interests
Data Efficient Learning, Open-endedness, Alignment, AI Safety, Mechanical Interpretability
Recent Activity
updated
a model
16 days ago
rshwndsz/gemma-3-4b-it-ckpt-int8
published
a model
16 days ago
rshwndsz/gemma-3-4b-it-ckpt-int8
updated
a model
20 days ago
rshwndsz/gemma-3-4b-it-ckpt
Organizations
None yet
models
103
rshwndsz/gemma-3-4b-it-ckpt-int8
Updated
rshwndsz/gemma-3-4b-it-ckpt
Updated
rshwndsz/gemma-3-4b-it-qat-q4_0-w4a16-g128
2B
•
Updated
•
7
rshwndsz/gemma-3-1b-pt-SFT-RM_MRG-ra
1.0B
•
Updated
•
2
rshwndsz/gemma-3-1b-pt-SFT-RM-ra
1.0B
•
Updated
•
1
rshwndsz/gemma-3-1b-pt-SFT-RM_MRG-si
1.0B
•
Updated
•
3
rshwndsz/gemma-3-1b-pt-SFT-RM-si
1.0B
•
Updated
•
1
rshwndsz/gemma-3-1b-pt-SFT-RM_MRG-bm
1.0B
•
Updated
•
2
rshwndsz/gemma-3-1b-pt-SFT-RM-bm
1.0B
•
Updated
•
1
rshwndsz/gemma-3-1b-pt-SFT-RM-bi
1.0B
•
Updated
•
1
datasets
21
rshwndsz/ambrosia-ranking-formatted
Viewer
•
Updated
•
250k
•
7
rshwndsz/ambrosia-single-formatted-grpo
Viewer
•
Updated
•
251k
•
4
rshwndsz/ambrosia-ranking-formatted-grpo
Viewer
•
Updated
•
250k
•
3
rshwndsz/ambrosia-binarymagn-formatted-grpo
Viewer
•
Updated
•
119k
•
6
rshwndsz/ambrosia-binary-formatted-grpo
Viewer
•
Updated
•
154k
•
3
rshwndsz/ambrosia-single-formatted-extended
Viewer
•
Updated
•
250k
•
5
rshwndsz/ambrosia-binary
Viewer
•
Updated
•
154k
•
13
rshwndsz/ambrosia-binary-formatted
Viewer
•
Updated
•
154k
•
3
rshwndsz/ambrosia-binarymagn
Viewer
•
Updated
•
119k
•
14
rshwndsz/ambrosia-binarymagn-formatted
Viewer
•
Updated
•
119k
•
5